Analysis of breast cancer classification using machine learning techniques and hyper parameter tuning

Breast cancer remains an important public health issue, emphasizing the need for accurate and timely diagnostic methods. It is mainly characterised by BRCA gene mutations due to genetic alterations specifically BRCA1 and BRCA2 genes which maintains healthy state responsible for DNA repair in the cells. When these genes undergo mutation, they lose the ability in cellular repair mechanisms thus leading to cancer development in the target cells which is observed biologically by differential gene expression analysis or by studying the cellular morphology differences between normal and cancerous cells. In this research project, we propose a machine learning classification (ML) method to detect breast cancer based on nuclear measurements from biopsy samples due to its predictive capability to detect patterns from a given dataset and categorise types of data based on their distribution. Based on a comprehensive set of ten nuclear features, we aim to distinguish malignant mass from benign mass, providing a reliable tool for early detection and improving patient outcomes between malignant and benign tumor stages. Early detection of malignancies leads to timely intervention, potentially reducing disease progression and improving patient survival rates. In addition, the non-invasive nature of biopsy sampling coupled with the efficiency of our ML model allows for simple and accessible breast cancer screening in a variety of clinical settings. In summary, our study demonstrates the capability of ML techniques to revolutionize breast cancer detection. The potency of nuclear measurements into our classification model provides a powerful and reliable tool for early diagnosis, improving patient outcomes and enhancing breast cancer screening methods. Ultimately, we envision this technology contributing to a proactive, data-driven approach to the diagnose against breast cancer, providing contribution to be proactive for a future with detection, treatment and care.